TDIUC

The TDIUC dataset is a benchmark used to evaluate Visual Question Answering (VQA) systems, containing diverse visual and textual data for assessing multi-modal interactions.

Papers using TDIUC (4)

MUREL: Multimodal Relational Reasoning for Visual Question Answering2019 · 24 citesCompact Trilinear Interaction for Visual Question Answering2019 · 14 citesVQA with Cascade of Self- and Co-Attention Blocks2023Question-Agnostic Attention for Visual Question Answering2019